© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 668
    Prev
    Next
    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (especially floating-point numbers and other numerical values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -ons
    -0.06
    !
    -0.06
    parated
    -0.06
    .Option
    -0.06
     neglig
    -0.06
    정을
    -0.06
    VE
    -0.06
    ning
    -0.06
     ITE
    -0.06
    \Core
    -0.06
    POSITIVE LOGITS
     Simpson
    0.06
    ört
    0.06
    ерами
    0.06
     Aless
    0.06
    Tipo
    0.06
    _pemb
    0.06
     частини
    0.06
     الشركة
    0.06
    주시
    0.05
     Darkness
    0.05
    Activations Density 0.176%

    No Known Activations